Status

We show the instrument.

You will not find polished traction on this page. batoon measures itself repeatably against a catalogue of 94 enterprise capabilities, eight layers and 13 industry scenarios. The result is here in full, including the half that is still missing.

As of August 2026

What runs

A substantial prototype, not a concept deck.

Three scenarios end to end, across two tenants

A product launch for a B2B SaaS company. A churn rescue for an online retailer, with a call centre under a capacity limit and with vetoes from consent and suppression lists. A creative-ops loop from brief through three variants to approval. All three run in a curated simulated world.

Real agents, not a scripted demo

The runs orchestrate AI agents. There is also a deterministic mode with no model access. It makes the same demonstration reproducible without an API key.

Five real MarTech systems connected

Canva, Mailchimp, Meta Ads, HubSpot and Google BigQuery, each read-and-draft only. Nothing is sent, no campaign launches.

Multi-tenant, with a real login

batoon is an OIDC relying party. It stores no passwords and runs no user directory of its own. Rights come from company and project role together: read, approve, configure.

The measurement

51.2 % of 94 capabilities.

51.2 %

471 of 920 points · 2 of 13 industry scenarios feasible without change · 18 critical gaps

By layer

Human–agent interaction 65 %
Orchestration & governance 64 %
Measurement 41 %
Distribution 39 %
Data layer 33 %

What is strong is what the product promise is about. What is weak is what a prototype cannot prove without real customer data and without live execution.

What is missing

The gaps, unvarnished.

Data layer — 33 %: The weakest layer. Without real customer data, identity resolution, data quality and broad warehouse integration are missing.
Distribution — 39 %: The consequence of the decision against live execution. The path is built and tested, but not armed.
Measurement — 41 %: The holdout mechanics are in place. What is missing is measurement over longer horizons and against real revenue figures.
No proof of scale: The scenarios run on segments of roughly a hundred contacts, not millions.
No enterprise IdP in use: OIDC is implemented and tested against a Keycloak profile. It has never run against the identity provider of a real corporation.
We set the assessment ourselves: The catalogue of 94 capabilities is ours. That makes the number internally comparable and reliable over time. It does not replace external review.

Guardrail

What this page does not claim.

No live execution. Nothing is sent, no campaign launches.
No paying customers, no references, no case studies.
No results from production use. The scenarios run in a simulated world.

We name these limits because they would surface in any review anyway. The prototype does without such claims.